Quantification of facial symmetry in orthognathic surgery: A novel approach integrating 3D contour maps and hyper-dimensional computing

This study aimed to enhance the evaluation of facial symmetry crucial for planning and assessing outcomes of orthognathic surgery (OGS). An innovative approach combining three-dimensional (3D) facial contour lines with hyperdimensional (HD) computing was developed for this purpose. Data were collected using 3D cone beam computed tomography (CBCT) at Chang Gung Memorial Hospital from 2016 to 2021. A comprehensive dataset was compiled, including images from 150 normal individuals and 2500 patients, totaling 5150 preoperative and postoperative facial images. A machine learning model was trained to analyze these images, and 3D contour data were used to create a facial symmetry quantification system with HD computing. Additionally, 3D CBCT data from 200 patients before and after OGS were retrospectively reviewed for clinical application. The developed facial symmetry algorithm demonstrated an overall accuracy of 84.1 %. Postoperative facial symmetry scores improved significantly, with a mean score increase of 53 %, from 2.40 to 3.63. The study culminated in the creation of a web-based system that leverages HD computing and 3D contour mapping to automate facial symmetry assessment. This system offers a user-friendly interface for rapid and accurate evaluations, facilitating better communication between clinicians and patients.